GLM-4.7 Server starts but errors out at inferencing

### Reminder

- [x] I have read the above rules and searched the existing issues.

### System Info

Pulled both kt-kernel and sglang on December 23 2025 and setup fresh conda environment and built it. When processing a prompt it fails.

# System Specifications for Hybrid CPU/GPU Inference

## System Overview
**OS:** Ubuntu 24.04.3 LTS
**Kernel:** Linux 6.14.0-37-generic

---

## Motherboard Specifications
**Model:** ASUS Pro WS W790E-SAGE SE
- **Platform:** Intel W790 Chipset
- **Socket:** LGA4677 (supports Intel Xeon W-3000 series)
- **Memory Slots:** 8x DDR5 DIMM slots
- **Memory Speed:** Support for DDR5-4800+ (OC capable)
- **PCIe Slots:** 7 PCIe 5.0 x16 slots for dual GPU setup
- **Form Factor:** Extended ATX

---

## CPU Specifications
**Processor:** Intel Xeon w9-3495X
- **Cores:** 56 physical cores / 112 threads
- **Base Frequency:** 800 MHz
- **Max Frequency:** 4.8 GHz
- **AVX-512 Support:** Full support
- **AMX (Advanced Matrix Extensions):** Full support
- **NUMA Nodes:** 1
---

## GPU Specifications
**Graphics Cards:** 2x NVIDIA RTX PRO 6000 Black Edition
- **VRAM per GPU:** 96 GB
- **Driver Version:** 580.95.05
- **CUDA Version:** 13.0
- **Power Consumption:** 600W max each

---

## Memory Configuration
**Total RAM:** 512 GB
**Memory Type:** DDR5 (8x DIMM slots populated)
**Memory Speed:** DDR5-4800+ (OC capable)
**OC Supported:** 6000 OC Stable
**Swap:** 0 GB (disabled)
**Memory Architecture:** 8-channel DDR5 configuration
**Available for Inference:** 503 GB total capacity for model loading

---

## Storage Configuration
**Primary Storage:**
- **System Drive:** WD_BLACK SN850X 2000GB (1.8TB)
- Mount: `/` (root filesystem)
- **Data Drive:** Samsung SSD 9100 PRO 4TB (3.6TB)
- Mount: `/media/mukul/data`

**Secondary Storage:**
- **Crucial Drive:** CT4000X10PROSSD9 (3.6TB)
- Mount: `/media/mukul/crucial`
- **External T7:** PSSD T7 Shield (3.6TB)
- Mount: `/media/mukul/t7`

---

### Reproduction

```text
```bash
(kt-kernel) mukul@jarvis:~$ CUDA_VISIBLE_DEVICES=0 PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True SGLANG_ENABLE_JIT_DEEPGEMM=0
python3 -m sglang.launch_server \
--host 0.0.0.0 \
--port 10002 \
--model /media/mukul/data/models/zai-org/GLM-4.7 \
--trust-remote-code \
--tool-call-parser glm \
--reasoning-parser glm45 \
--mem-fraction-static 0.92 \
--chunked-prefill-size 4096 \
--served-model-name jarvis-thinker \
--enable-mixed-chunk \
--attention-backend flashinfer \
--kt-method AMXINT4 \
--kt-weight-path /media/mukul/data/models/zai-org/GLM-4.7-AMXINT4 \
--kt-cpuinfer 56 \
--kt-threadpool-count 1 \
--kt-num-gpu-experts 4 \
--kt-max-deferred-experts-per-token 1
[2025-12-23 03:31:05] server_args=ServerArgs(model_path='/media/mukul/data/models/zai-org/GLM-4.7', tokenizer_path='/media/mukul/data/models/zai-org/GLM-4.7', tokenizer_mode='auto', tokenizer_worker_num=1, skip_tokenizer_init=False, load_format='auto', model_loader_extra_config='{}', trust_remote_code=True, context_length=None, is_embedding=False, enable_multimodal=None, limit_mm_data_per_request=None, revision=None, model_impl='auto', host='0.0.0.0', port=10002, fastapi_root_path='', grpc_mode=False, skip_server_warmup=False, warmups=None, nccl_port=None, checkpoint_engine_wait_weights_before_ready=False, dtype='auto', quantization=None, quantization_param_path=None, kv_cache_dtype='auto', enable_fp32_lm_head=False, modelopt_quant=None, modelopt_checkpoint_restore_path=None, modelopt_checkpoint_save_path=None, modelopt_export_path=None, quantize_and_serve=False, rl_quant_profile=None, mem_fraction_static=0.92, max_running_requests=None, max_queued_requests=None, max_total_tokens=None, chunked_prefill_size=4096, enable_dynamic_chunking=False, max_prefill_tokens=16384, prefill_max_requests=None, schedule_policy='fcfs', enable_priority_scheduling=False, abort_on_priority_when_disabled=False, schedule_low_priority_values_first=False, priority_scheduling_preemption_threshold=10, schedule_conservativeness=1.0, page_size=1, hybrid_kvcache_ratio=None, swa_full_tokens_ratio=0.8, disable_hybrid_swa_memory=False, radix_eviction_policy='lru', device='cuda', tp_size=1, pp_size=1, pp_max_micro_batch_size=None, pp_async_batch_depth=0, stream_interval=1, stream_output=False, random_seed=709364858, constrained_json_whitespace_pattern=None, constrained_json_disable_any_whitespace=False, watchdog_timeout=300, soft_watchdog_timeout=None, dist_timeout=None, download_dir=None, base_gpu_id=0, gpu_id_step=1, sleep_on_idle=False, custom_sigquit_handler=None, log_level='info', log_level_http=None, log_requests=False, log_requests_level=2, crash_dump_folder=None, show_time_cost=False, enable_metrics=False, enable_metrics_for_all_schedulers=False, tokenizer_metrics_custom_labels_header='x-custom-labels', tokenizer_metrics_allowed_custom_labels=None, bucket_time_to_first_token=None, bucket_inter_token_latency=None, bucket_e2e_request_latency=None, collect_tokens_histogram=False, prompt_tokens_buckets=None, generation_tokens_buckets=None, gc_warning_threshold_secs=0.0, decode_log_interval=40, enable_request_time_stats_logging=False, kv_events_config=None, enable_trace=False, otlp_traces_endpoint='localhost:4317', export_metrics_to_file=False, export_metrics_to_file_dir=None, api_key=None, served_model_name='jarvis-thinker', weight_version='default', chat_template=None, completion_template=None, file_storage_path='sglang_storage', enable_cache_report=False, reasoning_parser='glm45', tool_call_parser='glm', tool_server=None, sampling_defaults='model', dp_size=1, load_balance_method='round_robin', load_watch_interval=0.1, prefill_round_robin_balance=False, dist_init_addr=None, nnodes=1, node_rank=0, json_model_override_args='{}', preferred_sampling_params=None, enable_lora=None, max_lora_rank=None, lora_target_modules=None, lora_paths=None, max_loaded_loras=None, max_loras_per_batch=8, lora_eviction_policy='lru', lora_backend='csgmv', max_lora_chunk_size=16, attention_backend='flashinfer', decode_attention_backend=None, prefill_attention_backend=None, sampling_backend='flashinfer', grammar_backend='xgrammar', mm_attention_backend=None, fp8_gemm_runner_backend='auto', nsa_prefill_backend='flashmla_sparse', nsa_decode_backend='fa3', disable_flashinfer_autotune=False, speculative_algorithm=None, speculative_draft_model_path=None, speculative_draft_model_revision=None, speculative_draft_load_format=None, speculative_num_steps=None, speculative_eagle_topk=None, speculative_num_draft_tokens=None, speculative_accept_threshold_single=1.0, speculative_accept_threshold_acc=1.0, speculative_token_map=None, speculative_attention_mode='prefill', speculative_draft_attention_backend=None, speculative_moe_runner_backend='auto', speculative_moe_a2a_backend=None, speculative_draft_model_quantization=None, speculative_ngram_min_match_window_size=1, speculative_ngram_max_match_window_size=12, speculative_ngram_min_bfs_breadth=1, speculative_ngram_max_bfs_breadth=10, speculative_ngram_match_type='BFS', speculative_ngram_branch_length=18, speculative_ngram_capacity=10000000, enable_multi_layer_eagle=False, ep_size=1, moe_a2a_backend='none', moe_runner_backend='auto', flashinfer_mxfp4_moe_precision='default', enable_flashinfer_allreduce_fusion=True, deepep_mode='auto', ep_num_redundant_experts=0, ep_dispatch_algorithm=None, init_expert_location='trivial', enable_eplb=False, eplb_algorithm='auto', eplb_rebalance_num_iterations=1000, eplb_rebalance_layers_per_chunk=None, eplb_min_rebalancing_utilization_threshold=1.0, expert_distribution_recorder_mode=None, expert_distribution_recorder_buffer_size=1000, enable_expert_distribution_metrics=False, deepep_config=None, moe_dense_tp_size=None, elastic_ep_backend=None, mooncake_ib_device=None, max_mamba_cache_size=None, mamba_ssm_dtype='float32', mamba_full_memory_ratio=0.9, mamba_scheduler_strategy='no_buffer', mamba_track_interval=256, enable_hierarchical_cache=False, hicache_ratio=2.0, hicache_size=0, hicache_write_policy='write_through', hicache_io_backend='kernel', hicache_mem_layout='layer_first', hicache_storage_backend=None, hicache_storage_prefetch_policy='best_effort', hicache_storage_backend_extra_config=None, enable_lmcache=False, kt_weight_path='/media/mukul/data/models/zai-org/GLM-4.7-AMXINT4', kt_method='AMXINT4', kt_cpuinfer=56, kt_threadpool_count=1, kt_num_gpu_experts=4, kt_max_deferred_experts_per_token=1, dllm_algorithm=None, dllm_algorithm_config=None, enable_double_sparsity=False, ds_channel_config_path=None, ds_heavy_channel_num=32, ds_heavy_token_num=256, ds_heavy_channel_type='qk', ds_sparse_decode_threshold=4096, cpu_offload_gb=0, offload_group_size=-1, offload_num_in_group=1, offload_prefetch_step=1, offload_mode='cpu', multi_item_scoring_delimiter=None, disable_radix_cache=False, cuda_graph_max_bs=256, cuda_graph_bs=[1, 2, 4, 8, 12, 16, 24, 32, 40, 48, 56, 64, 72, 80, 88, 96, 104, 112, 120, 128, 136, 144, 152, 160, 168, 176, 184, 192, 200, 208, 216, 224, 232, 240, 248, 256], disable_cuda_graph=False, disable_cuda_graph_padding=False, enable_profile_cuda_graph=False, enable_cudagraph_gc=False, enable_layerwise_nvtx_marker=False, enable_nccl_nvls=False, enable_symm_mem=False, disable_flashinfer_cutlass_moe_fp4_allgather=False, enable_tokenizer_batch_encode=False, disable_tokenizer_batch_decode=False, disable_outlines_disk_cache=False, disable_custom_all_reduce=False, enable_mscclpp=False, enable_torch_symm_mem=False, disable_overlap_schedule=False, enable_mixed_chunk=True, enable_dp_attention=False, enable_dp_lm_head=False, enable_two_batch_overlap=False, enable_single_batch_overlap=False, tbo_token_distribution_threshold=0.48, enable_torch_compile=False, enable_piecewise_cuda_graph=False, enable_torch_compile_debug_mode=False, torch_compile_max_bs=32, piecewise_cuda_graph_max_tokens=4096, piecewise_cuda_graph_tokens=[4, 8, 12, 16, 20, 24, 28, 32, 48, 64, 80, 96, 112, 128, 144, 160, 176, 192, 208, 224, 240, 256, 288, 320, 352, 384, 416, 448, 480, 512, 640, 768, 896, 1024, 1152, 1280, 1408, 1536, 1664, 1792, 1920, 2048, 2176, 2304, 2432, 2560, 2688, 2816, 2944, 3072, 3200, 3328, 3456, 3584, 3712, 3840, 3968, 4096], piecewise_cuda_graph_compiler='eager', torchao_config='', enable_nan_detection=False, enable_p2p_check=False, triton_attention_reduce_in_fp32=False, triton_attention_num_kv_splits=8, triton_attention_split_tile_size=None, num_continuous_decode_steps=1, delete_ckpt_after_loading=False, enable_memory_saver=False, enable_weights_cpu_backup=False, enable_draft_weights_cpu_backup=False, allow_auto_truncate=False, enable_custom_logit_processor=False, flashinfer_mla_disable_ragged=False, disable_shared_experts_fusion=False, disable_chunked_prefix_cache=False, disable_fast_image_processor=False, keep_mm_feature_on_device=False, enable_return_hidden_states=False, enable_return_routed_experts=False, scheduler_recv_interval=1, numa_node=None, enable_deterministic_inference=False, rl_on_policy_target=None, enable_attn_tp_input_scattered=False, enable_nsa_prefill_context_parallel=False, enable_fused_qk_norm_rope=False, enable_dynamic_batch_tokenizer=False, dynamic_batch_tokenizer_batch_size=32, dynamic_batch_tokenizer_batch_timeout=0.002, debug_tensor_dump_output_folder=None, debug_tensor_dump_layers=None, debug_tensor_dump_input_file=None, debug_tensor_dump_inject=False, disaggregation_mode='null', disaggregation_transfer_backend='mooncake', disaggregation_bootstrap_port=8998, disaggregation_decode_tp=None, disaggregation_decode_dp=None, disaggregation_prefill_pp=1, disaggregation_ib_device=None, disaggregation_decode_enable_offload_kvcache=False, disaggregation_decode_enable_fake_auto=False, num_reserved_decode_tokens=512, disaggregation_decode_polling_interval=1, encoder_only=False, language_only=False, encoder_transfer_backend='zmq_to_scheduler', encoder_urls=[], custom_weight_loader=[], weight_loader_disable_mmap=False, remote_instance_weight_loader_seed_instance_ip=None, remote_instance_weight_loader_seed_instance_service_port=None, remote_instance_weight_loader_send_weights_group_ports=None, remote_instance_weight_loader_backend='nccl', remote_instance_weight_loader_start_seed_via_transfer_engine=False, enable_pdmux=False, pdmux_config_path=None, sm_group_num=8, mm_max_concurrent_calls=32, mm_per_request_timeout=10.0, enable_broadcast_mm_inputs_process=False, enable_prefix_mm_cache=False, mm_enable_dp_encoder=False, mm_process_config={}, decrypted_config_file=None, decrypted_draft_config_file=None, forward_hooks=None)
[2025-12-23 03:31:06] Using default HuggingFace chat template with detected content format: openai
[2025-12-23 03:31:11] Init torch distributed begin.
[Gloo] Rank 0 is connected to 0 peer ranks. Expected number of connected peer ranks is : 0
[Gloo] Rank 0 is connected to 0 peer ranks. Expected number of connected peer ranks is : 0
[Gloo] Rank 0 is connected to 0 peer ranks. Expected number of connected peer ranks is : 0
[Gloo] Rank 0 is connected to 0 peer ranks. Expected number of connected peer ranks is : 0
[2025-12-23 03:31:11] Init torch distributed ends. mem usage=0.00 GB
[2025-12-23 03:31:12] Ignore import error when loading sglang.srt.models.glmasr: cannot import name 'GlmasrConfig' from 'transformers' (/home/mukul/miniconda3/envs/kt-kernel/lib/python3.11/site-packages/transformers/__init__.py)
[2025-12-23 03:31:12] Load weight begin. avail mem=93.24 GB
[2025-12-23 03:31:12] Shared experts fusion optimization enabled.
CPUInfer[0x122eae50]: Hello
WorkerPool[0x24291e90] 1 subpools, [numa:threads][0:56]
===========In NumaPool============
In Numa Worker Pool at NUMA 0, 56 threads
Loading safetensors checkpoint shards: 0% Completed | 0/93 [00:00", line 0, in __tvm_ffi_merge_state
File "/home/mukul/miniconda3/envs/kt-kernel/lib/python3.11/site-packages/flashinfer/data/csrc/cascade.cu", line 53, in merge_state(tvm::ffi::TensorView, tvm::ffi::TensorView, tvm::ffi::TensorView, tvm::ffi::TensorView, tvm::ffi::TensorView, tvm::ffi::TensorView)::::
TVM_FFI_ICHECK(status == cudaSuccess)

RuntimeError: Check failed: (status == cudaSuccess) is false: MergeState kernel launch failed: invalid argument

[2025-12-23 03:33:04] SIGQUIT received. signum=None, frame=None. It usually means one child failed.
Killed
```
```

### Others

_No response_

Reproduce the failure using the provided `python3 -m sglang.launch_server` command and capture the complete inference traceback, which is not included in the issue body. Compare the behavior with the specified GLM-4.7, AMXINT4, CUDA, and flashinfer configuration; done means identifying the failing component and confirming that a prompt completes successfully.

Written by the indexing model from the issue text.